Application of Statistical Model Checking for Robustness Comparison of Power Electronics Controllers

Power electronic-based systems exhibit non-linear dynamics requiring simultaneous control of multiple control objectives. It is therefore expected that controllers that can cope with those nonlinearities will have a better performance than controllers requiring system linearization or nesting of the control objectives in a cascaded structure. However, the problem remains how to quantify their robustness and make a fair comparison between different non-linear controllers. The conventional tools used for the robustness validation of linear controllers cannot directly be applied to different non-linear controllers. Therefore, this paper demonstrates an approach based on statistical model checking for performing controller comparisons. The performance and robustness of different controllers (linear, model predictive, and neural networks-based) were compared in the same stochastic environment. Using this approach, a statistical estimate can be obtained for how the controller performance will be affected under different scenarios.